Predicting bowel function after diverting stoma closure in patients with rectal cancer.

Background: Patients with rectal cancer undergoing laparoscopic anterior resection and diverting stomas often suffer from bowel dysfunction after stoma closure, impairing their quality of life. This study aims to develop a machine learning tool to predict bowel function after diverting stoma closure. Methods: Clinicopathological data and post-operative follow-up information from patients with mid-low rectal cancer after diverting stoma closure were collected and analyzed. Patients were randomly divided into training and test sets in a 7:3 ratio. A machine learning model was developed in the training set to predict major low anterior resection syndrome (LARS) and evaluated in the test set. Decision curve analysis (DCA) was used to assess clinical utility. Results: The study included 396 eligible patients who underwent laparoscopic anterior resection and diverting stoma in Tongji Hospital affiliated with Huazhong University of Science and Technology from 1 January 2012 to 31 December 2020. The interval between stoma creation and closure, neoadjuvant therapy, and body mass index were identified as the three most crucial characteristics associated with patients experiencing major LARS in our cohort. The machine learning model achieved an area under the receiver operating characteristic curve (AUC) of 0.78 [95% confidence interval (CI): 0.74-0.83] in the training set (n=277) and 0.74 (95% CI: 0.70-0.79) in the test set (n=119), and area under the precision-recall curve (AUPRC) of 0.73 and 0.69, respectively, with sensitivity of 0.67 and specificity of 0.66 for the test set. DCA confirmed clinical applicability. Conclusions: This study developed a machine learning model to predict major LARS in rectal cancer patients after diverting stoma closure, aiding their decision-making and counseling.

Collecting duct carcinoma with retroperitoneal mass as initial presentation: a rare case report.

BACKGROUND: Collecting duct carcinoma (CDC) is a rare renal tumor, originating from the distal collecting duct. CDC rarely presents as a primary tumor outside the renal system. CASE PRESENTATION: In this study, we report a rare case of collecting duct carcinoma, with an initial presentation of retroperitoneal lymph node metastasis, and no identifiable primary renal tumor on CT, at the time of diagnosis. The patient was a 64-year-old man presenting with lower back pain. Preoperative CT showed a round, soft tissue mass, measuring 6.7 × 4.4 × 3.3 cm, in the left retroperitoneum with no exact occupying lesion in the left kidney. Clinically, ectopic pheochromocytoma was considered to be a differential diagnosis, and tumor resection was performed. Postoperative pathological results demonstrated that the mass was a fused lymph node, and the tumor cells were destroying the structure. The final diagnosis was lymph node metastatic collecting duct carcinoma, by histology and immunohistochemistry. No further treatment was performed as no space occupying lesion was found in the kidney. Three months later, CT was reexamined, and a mass of 3.6 cm in diameter, was found in the lower left kidney, along with multiple soft tissue masses, in the left renal hilum. Considering recurrence or metastasis, the patient was recommended to undergo surgical treatment, but the patient refused. Four months later, CT was re-examined. The tumor had rapidly progressed but the patient refused treatment again. As per the author's press release (eleven months after the first discovery), the patient is still alive. CONCLUSION: CDC is a rare malignant renal carcinoma, with a high chance of rapid progress, regional lymph nodes involvement and metastasis. It presents diagnostic challenges to clinicians and pathologists, particularly, in the absence of radiographically detectable intrarenal lesions. Definite diagnosis is based on pathological examination combined with immunohistochemical staining.

Machine learning model for prediction of low anterior resection syndrome following laparoscopic anterior resection of rectal cancer: A multicenter study.

BACKGROUND: Low anterior resection syndrome (LARS) severely impairs patient postoperative quality of life, especially major LARS. However, there are few tools that can accurately predict major LARS in clinical practice. AIM: To develop a machine learning model using preoperative and intraoperative factors for predicting major LARS following laparoscopic surgery of rectal cancer in Chinese populations. METHODS: Clinical data and follow-up information of patients who received laparoscopic anterior resection for rectal cancer from two medical centers (one discovery cohort and one external validation cohort) were included in this retrospective study. For the discovery cohort, the machine learning prediction algorithms were developed and internally validated. In the external validation cohort, we evaluated the trained model using various performance metrics. Further, the clinical utility of the model was tested by decision curve analysis. RESULTS: Overall, 1651 patients were included in the present study. Anastomotic height, neoadjuvant therapy, diverting stoma, body mass index, clinical stage, specimen length, tumor size, and age were the risk factors associated with major LARS. They were used to construct the machine learning model to predict major LARS. The trained random forest (RF) model performed with an area under the curve of 0.852 and a sensitivity of 0.795 (95%CI: 0.681-0.877), a specificity of 0.758 (95%CI: 0.671-0.828), and Brier score of 0.166 in the external validation set. Compared to the previous preoperative LARS score model, the current model exhibited superior predictive performance in predicting major LARS in our cohort (accuracy of 0.772 for the RF model vs 0.355 for the preoperative LARS score model). CONCLUSION: We developed and validated a robust tool for predicting major LARS. This model could potentially be used in the clinic to identify patients with a high risk of developing major LARS and then improve the quality of life.

Artificial intelligence assists surgeons' decision-making of temporary ileostomy in patients with rectal cancer who have received anterior resection.

BACKGROUND: Due to the difficult evaluation of the risk of anastomotic leakage (AL) after rectal cancer resection, the decision to perform a temporary ileostomy is not easily distinguishable. The aim of the present study was to develop an artificial intelligence (AI) model for identifying the risk of AL to assist surgeons in the selective implementation of a temporary ileostomy. MATERIALS AND METHODS: The data from 2240 patients with rectal cancer who received anterior resection were collected, and these patients were divided into one training and two test cohorts. Five AI algorithms, such as support vector machine (SVM), logistic regression (LR), Naive Bayes (NB), stochastic gradient descent (SGD) and random forest (RF) were employed to develop predictive models using clinical variables and were assessed using the two test cohorts. RESULTS: The SVM model indicated good discernment of AL, and might have increased the implementation of temporary ileostomy in patients with AL in the training cohort (p < 0.001). Following the assessment of the two test cohorts, the SVM model could identify AL in a favorable manner, which performed with positive predictive values of 0.150 (0.091-0.234) and 0.151 (0.091-0.237), and negative predictive values of 0.977 (0.958-0.988) and 0.986 (0.969-0.994), respectively. It is important to note that the implementation of temporary ileostomy in patients without AL would have been significantly reduced (p < 0.001) and which would have been significantly increased in patients with AL (p < 0.05). CONCLUSION: The model (https://alrisk.21cloudbox.com/) indicated good discernment of AL, which may be used to assist the surgeon's decision-making of performing temporary ileostomy.

Pre-Vascularized Electrospun Graphene Oxide-Gelatin Chamber for Intestinal Wall Defect Repair.

PURPOSE: Successful intestinal tissue engineering requires specialized biocompatible scaffolds and a vibrant vascularization microenvironment. A pre-vascularized chamber can provide both in vivo, but there is little report on using it to improve intestinal regeneration. Besides, researchers have found that gelatin is highly biocompatible and graphene oxide (GO) can be used to improve mechanical properties. Thus, applying a pre-vascularized chamber fabricated gelatin and GO into intestinal tissue engineering is worth a try. MATERIALS AND METHODS: In this study, an investigation into the physicochemical and mechanical properties as well as biocompatibility of the electrospun graphene oxide-gelatin (GO-Gel) scaffolds were conducted in vitro. Meanwhile, a pre-vascularized GO-Gel (V-GO-Gel) chamber model was built by implanting the scaffold around the mesenteric vessels in rat. After vascularization process, the chamber was used to repair the perforation and then assessed by histology and immunofluorescence analyses. RESULTS: These porous scaffolds were mechanical improved with GO incorporated into gelatin. Further, the cell adherence, viability and morphology on the scaffolds were maintained. The V-GO-Gel chamber model was successfully built and effective enhanced the repair of the intestinal wall than the other group without recurrence or complications. CONCLUSION: The V-GO-Gel chamber shows promising therapeutic potential in the repair of intestinal wall defects.

Application of Machine Learning for Predicting Anastomotic Leakage in Patients with Gastric Adenocarcinoma Who Received Total or Proximal Gastrectomy.

Anastomotic leakage is a life-threatening complication in patients with gastric adenocarcinoma who received total or proximal gastrectomy, and there is still no model accurately predicting anastomotic leakage. In this study, we aim to develop a high-performance machine learning tool to predict anastomotic leakage in patients with gastric adenocarcinoma received total or proximal gastrectomy. A total of 1660 cases of gastric adenocarcinoma patients who received total or proximal gastrectomy in a large academic hospital from 1 January 2010 to 31 December 2019 were investigated, and these patients were randomly divided into training and testing sets at a ratio of 8:2. Four machine learning models, such as logistic regression, random forest, support vector machine, and XGBoost, were employed, and 24 clinical preoperative and intraoperative variables were included to develop the predictive model. Regarding the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy, random forest had a favorable performance with an AUC of 0.89, a sensitivity of 81.8% and specificity of 82.2% in the testing set. Moreover, we built a web app based on random forest model to achieve real-time predictions for guiding surgeons' intraoperative decision making.

Anodic electrogenerated chemiluminescence behavior and the choline biosensing application of blue emitting conjugated polymer dots.

The anodic electrochemiluminescence (ECL) behavior of poly(9,9-dioctylfluorenyl-2,7-diyl) (PFO) dots was studied and applied in oxidoreductase-based ECL biosensing using Chox as the model enzyme.

A signal-on electrochemiluminescence biosensor for detecting Con A using phenoxy dextran-graphite-like carbon nitride as signal probe.

A novel signal-on electrochemiluminescence (ECL) biosensor for detecting concanavalin A (Con A) was fabricated with phenoxy dextran-graphite-like carbon nitride (DexP-g-C3N4) as signal probe. In this construction strategy, the nanocomposites of three-dimensional graphene and gold nanoparticles (3D-GR-AuNPs) were used as matrix for high loading of glucose oxidase (GOx), which served as recognition element for bounding Con A. Con A further interacted with DexP-g-C3N4 through a specific carbohydrate-Con A interaction to achieve a sandwiched scheme. With the increase of Con A incubated onto the electrode, the ECL signal resulted from DexP-g-C3N4 would enhance, thus achieving a signal-on ECL biosensor for Con A detection. Due to the integration of the virtues of 3D-GR-AuNPs and the excellent ECL performance of DexP-g-C3N4, the prepared biosensor exhibits a wide linear response range from 0.05 ng/mL to 100 ng/mL and a low detection limit of 17 pg/mL (S/N=3).

Enhanced electrochemiluminescence sensor for detecting dopamine based on gold nanoflower@graphitic carbon nitride polymer nanosheet-polyaniline hybrids.

In this work, an enhanced electrochemiluminescence (ECL) sensor based on gold nanoflower@graphitic carbon nitride polymer nanosheet-polyaniline hybrids (AuNF@g-C3N4-PANI) was prepared for the detection of dapamine (DA). First, the bulk g-C3N4 was prepared through polymerizing melamine under 600 °C. And then the g-C3N4 nanosheet was obtained by ultrasonication-assisted liquid exfoliation of bulk g-C3N4. Finally, polyaniline (PANI) and gold nanoflowers (AuNFs) were successively formed on the g-C3N4 nanosheet through an in situ synthesis method. The resulting AuNF@g-C3N4-PANI hybrids were modified onto the surface of glassy carbon electrode to achieve a sensor (AuNF@g-C3N4-PANI/GCE) for detecting dopamine. Under the optimal conditions, the ECL signal increased linearly with the concentration of dopamine. The linear range of 5.0 × 10(-9) to 1.6 × 10(-6) M was obtained, while the detection limit was 1.7 × 10(-9) M. The prepared sensor exhibited a low detection limit and high sensitivity for the determination of dopamine. The combination of g-C3N4 nanosheet, PANI and AuNF would provide a new opportunity for the ECL sensor.

An electrogenerated chemiluminescence sensor based on gold nanoparticles@C60 hybrid for the determination of phenolic compounds.

This paper described a novel strategy for the construction of an electrogenerated chemiluminescence (ECL) sensor based on gold nanoparticles@C60 (AuNPs@C60) hybrid for detecting phenolic compounds. First, C60 was functionalized with l-cysteine. Subsequently, with C60 as the core, gold nanoparticles (AuNPs) are synthesized and grown through an in situ reduction method in the presence of ascorbic acid (AA). The resulted flowerlike AuNPs@C60 nanoparticles were modified onto the glassy carbon electrode to achieve the sensor (AuNPs@C60/GCE). Here, l-cysteine not only can improve the biocompatibility and hydrophilicity of C60 but also can enhance the electrogenerated chemiluminescence (ECL) of peroxydisulfate system. Furthermore, both AuNPs and C60 are also beneficial to the ECL of the peroxydisulfate system. Due to the combination of l-cysteine, AuNPs and C60, the proposed ECL sensor exhibited an excellent analytical performance. Under an optimum condition, the ECL intensity increased linearly with phenolic compounds. The linear ranges of 6.2 × 10(-8)-1.2 × 10(-4)M, 5.0 × 10(-8)-1.1 × 10(-4)M and 5.0 × 10(-8)-1.1 × 10(-4)M were obtained for catechol (CC), hydroquinone (HQ) and p-cresol (PC), respectively, and the detection limits were 2.1 × 10(-8)M, 1.5 × 10(-8)M and 1.7 × 10(-8)M, respectively. The AuNPs@C60 hybrid might hold a new opportunity to develop an ECL sensor.

Overoxidized polyimidazole/graphene oxide copolymer modified electrode for the simultaneous determination of ascorbic acid, dopamine, uric acid, guanine and adenine.

In the present work, a novel strategy based on overoxidized polyimidazole (PImox) and graphene oxide (GO) copolymer modified electrode was proposed for the simultaneous determination of ascorbic acid (AA), dopamine (DA), uric acid (UA), guanine (G) and adenine (A). The copolymer was characterized by the scanning electron microscopy (SEM), atomic force microscopy (AFM), Fourier transform infrared (FT-IR), X-ray photoelectron spectroscopy (XPS) and electrochemical impedance spectroscopy (EIS). Due to the synergistic effects between PImox and GO, the proposed electrode exhibited excellent electrochemical catalytic activities and high selectivity and sensitivity toward the oxidation of AA, DA, UA, G and A. The peak separations between AA and DA, AA and UA, UA and G, and G and A were 140 mV, 200 mV, 380 mV and 300 mV, respectively. The linear response ranges for AA, DA, UA, G and A were 75-2275 µM, 12-278 µM, 3.6-249.6 µM, 3.3-103.3 µM and 9.6-215 µM, respectively, and corresponding detection limits were 18 µM, 0.63 µM, 0.59 µM, 0.48 µM and 1.28 µM.